A system for generating wrap-up information is capable of learning how interactions are transformed into contact notes and outcome codes using natural language processing and can generate the contact notes and outcome codes for new incoming interactions by applying prediction models trained on interaction data, contact notes and outcome codes. The system for generating wrap-up information receives interaction data, including interaction audio data, interaction transcripts, associated contact notes and associated outcome codes. The interaction transcripts are generated from the previous interactions between agents and customers. The contact notes and outcome codes are generated by agents during the associated previous interactions. The system processes and uses the interaction data to train prediction models to analyze interaction audio data and interaction transcripts and predict appropriate contact notes and outcome codes for the interaction. Once trained the prediction model(s) can generate appropriate contact notes and outcome codes for new interactions.
The present invention allows a CEC system to automatedly track the use, storage, access, and modification of sensitive information/data in the system through desktop monitoring. Further, through desktop, video, and audio monitoring of CSRs the system can automatedly determine the improper use, access, storage, and modification of sensitive information by implementing sensitive data use rules that allow a system to be specialized for the user. Finally, the system can automatedly determine and implement violation actions for the improper use, storage, access, and manipulation of sensitive information. This provides an intelligent system capable of locating all sensitive data in the system and regulating the use, access, and storage of sensitive data in the system.
G06F 21/55 - Detecting local intrusion or implementing counter-measures
G06F 16/40 - Information retrieval; Database structures therefor; File system structures therefor of multimedia data, e.g. slideshows comprising image and additional audio data
G06F 21/62 - Protecting access to data via a platform, e.g. using keys or access control rules
3.
SYSTEM AND METHOD FOR DEVELOPING A COMMON INQUIRY RESPONSE
The present application includes a method and system for developing a common inquiry response. The system receives at least one customer contact formed by an inquiry and its response, analyzes the customer contact to determine the content of the inquiry and the response, and stores the inquiry and the response in a corresponding inquiry-response sub-database in an inquiry-response database. After analyzing at least one of the sub-databases, the system assigns a common inquiry-response (CIR) knowledge document to that inquiry-response sub-database for future use involving similar inquiries and responses. This allows a user to respond more quickly to inquiries with a reduced risk of incorrect or inconsistent information in the response.
The present invention is a system and method for organizing and integrating electronic customer service resources. A CEC system from a customer interaction receives data from a customer interaction and analyzes the data using a CAE incorporating a set of analytics rules before selecting a customer service module or a document from a document database based on the analysis. This data analysis and module or document selection repeats until all data received by the CEC system has been analyzed.
The present application includes a method and system for gathering customer information through games. The system transmits offers to play games over the contact medium used by the customer. The games are selected to elicit information from the customer; information ranging from the customer's mood to marketing information to security information. The information so obtained can be used to update client profiles.
The present invention is a method and system for automatically producing a form. Upon receiving at least one type of data input, the system analyzes the data input and produces a form based on the results of the analysis of the data input. This process may be used to either generate or update a form, and may be repeated to update an existing form.
An analysis platform combines unsupervised and semi-supervised approaches to quickly surface and organize relevant user intentions from conversational text (e.g., from natural language inputs). An unsupervised and semi-supervised pipeline is provided that integrates the fine-tuning of high performing language models via a language models fine-tuning module, a distributed KNN-graph building method via a KNN-graph building module, and community detection techniques for mining the intentions and topics from texts via an intention mining module.
A real-time conversation is monitored between a user and an intelligent virtual assistant (IVA). A visualization may be generated and displayed to the user on the user computing device based on one or more topics identified in the conversation. The conversation between the user and the IVA may continue and is continued to be monitored. The visualization can be updated as the conversation continues, e.g., based on further topics being identified.
A set of documents related to a particular topic, industry, or entity is received (210). Sentences are extracted from each document (215). The sentences are grouped into tuples of one, two, or three consecutive sentences (i.e., short text sequences) (220). The sentence tuples are clustered based on vector representations of the sentences (225). For each cluster, a set of tuples that best represents or best fits the cluster is selected (225). These sentence tuples are fed to an ontology to determine ontological entities associated with each tuple (230). These determined ontological entities are associated with the clusters corresponding to each tuple (230). The sentence tuples associated with each cluster are labeled based on the ontological entities associated with the cluster (235). The labeled sentence tuples may then be used for a variety of purposes such as training a model to determine the topic of short text sequences (240).
In one embodiment, certain words or phrases spoken by customers during calls to a call center are used to identify or authenticate the user. Words or phrases such as a customer's name, or an account number or telephone number, are selected for a customer. Recordings of the selected words or phrases spoken by the customer during previous calls are used to generate voiceprints that are stored and associated with the customer. Later, when the customer calls the call center, instances of the customer speaking the selected words are extracted from the call (referred to herein as "audio-of-interest") and are compared against the voiceprints stored for the customer. If the voiceprints match the audio-of-interest the customer is authenticated.
G06F 21/32 - User authentication using biometric data, e.g. fingerprints, iris scans or voiceprints
H04L 29/06 - Communication control; Communication processing characterised by a protocol
G06Q 20/40 - Authorisation, e.g. identification of payer or payee, verification of customer or shop credentials; Review and approval of payers, e.g. check of credit lines or negative lists
11.
SYSTEM AND METHOD OF SENTIMENT MODELING AND APPLICATION TO DETERMINE OPTIMIZED AGENT ACTION
The present invention is a system and method of continuous sentiment tracking and the determination of optimized agent actions through the training of sentiment models and applying the sentiment models to new incoming interactions. The system receives conversations comprising incoming interactions and agent actions and determines customer sentiment on a micro-interaction level for each incoming interaction. Based on interaction types, the system corelates the determined sentiment with the agent action received prior to the sentiment determination to create and train sentiment models. Sentiment models include agent action recommendations for a desired sentiment outcome. Once trained, the sentiment models can be applied to new incoming interactions to provide CSRs with actions that will yield a desired sentiment outcome.
A system and method for selecting an anomaly detection method from among a plurality of known anomaly detection methods includes selecting a set of anomaly detections methods based on characteristics of the time series, such as missing time steps, trend, drift, seasonality and concept drift. From among the applicable anomaly detection methods, the selection may be further informed by annotated predicted anomalies, and based on the annotations, turning the parameters for each respective anomaly detection method. Thereafter, the anomaly detection methods are scored and then further tuned according to human actions in identifying anomalies or disagrees with anomalies in the time series.
In the present disclosure, analytics are applied to work items while the work items are waiting in a work queue in order to optimize the routing and allocation of work items to agents in the most efficient manner possible, while optimizing agents being assigned to work items they are most qualified to handle. By performing a look ahead at more than the initial work item, the system assesses the agent skills required by imminent work items in the work queue. This is then compared to a skillset of each available and/or soon to be available agent in order to achieve the optimal allocation of the work items to maximize the work item being assigned the best qualified agent. The work items are then routed to the agents accordingly.In the present disclosure, analytics are applied to work items while the work items are waiting in a work queue in order to optimize the routing and allocation of work items to agents in the most efficient manner possible, while optimizing agents being assigned to work items they are most qualified to handle. By performing a look ahead at more than the initial work item, the system assesses the agent skills required by imminent work items in the work queue. This is then compared to a skillset of each available and/or soon to be available agent in order to achieve the optimal allocation of the work items to maximize the work item being assigned the best qualified agent. The work items are then routed to the agents accordingly.
An exemplary embodiment of the present application is a system and method for work allocation optimization. In the present disclosure, analytics are applied to work items while the work items are waiting in a work queue in order to optimize the routing and allocation of work items to agents in the most efficient manner possible, while optimizing the utilization of agents. By performing a look ahead at more than the initial work item, the system assesses the agent skills required by imminent work items in the work queue. This is then compared to a skillset of each available and/or soon to be available agent in order to achieve the optimal allocation of the work items to maximize utilization of agents. The work items are then routed to the agents accordingly.
In an embodiment, a method for authenticating calls and for preventing fraud is provided. The method includes: receiving a call through a first channel (705), wherein the call is associated with a customer and a speaker; determine if there are one or more voiceprints associated with the customer (710); if it is determined that there are one or more voiceprints associated with the customer: retrieving the one or more voiceprints associated with the customer (715); determine if voice data associated with the call matches any of the one or more voiceprints associated with the customer (720); and if the voice data matches any of the one or more voiceprints associated with the customer, flag the call as an authenticated call (725).
Systems and methods are provided framework for automatically choosing the appropriate generalized linear model (GLM) given a time series of count data, and for anomaly detection on time series data. A dispersion parameter is determined and used to determine whether the count data is overdispersed data or underdispersed data. The overdispersed data or the underdispersed data is used to determine a GLM to apply on the dataset. Using the determined GLM on the data, anomalies can be determined.
In an implementation, a method (200) for detecting anomalies in textual items is provided. The method includes: receiving a first plurality of textual items by a computing device (110) (210); training a language model using the received first plurality of textual items by the computing device (220); after training the language model, receiving a second plurality of textual items by the computing device (230); calculating a cross-entropy for each textual item in the second plurality of textual items by the computing device using the language model (240); and detecting an anomaly in at least one of the textual items of the second plurality of textual items by the computing device using the calculated cross-entropies (250).
A system is provided that uses location aware technologies in a variety of environments including retail environments and workplace environments. Location aware technologies associated with computing devices such as mobile phones are used to track users as they move within an environment (108). With respect to retail environments, a loyalty application (108) may be installed in the phone (105) of a customer that can provide the location of the customer to the retail environment. When it is determined that the customer is near the retail environment (410), a user profile associated with the customer can be used to select offers or promotions that can be displayed to the customer by the loyalty application to encourage the customer to enter the retail environment (430; 440; 450).
A scalable system provides automated conversation review that can identify potential miscommunications. The system may provide suggested actions to fix errors in intelligent virtual assistant (IVA) understanding, may prioritize areas of language model repair, and may automate the review of conversations. By the use of an automated system for conversation review, problematic interactions can be surfaced without exposing the entire set of conversation logs to human reviewers, thereby minimizing privacy invasion. A scalable system processes conversations and autonomously marks the interactions where the IVA is misunderstanding the user.
Real-time speech analytics (RTSA) provides maintaining real-time speech conditions, rules, and triggers, and real-time actions and alerts to take. A call between a user and an agent is received at an agent computing device. The call is monitored to detect in the call one of the real-time speech conditions, rules, and triggers. Based on the detection, at least one real-time action and/or alert is initiated.
H04M 3/42 - Systems providing special services or facilities to subscribers
G10L 25/63 - Speech or voice analysis techniques not restricted to a single one of groups specially adapted for particular use for comparison or discrimination for estimating an emotional state
Systems (110) and methods (200; 300) are described to combine two or more linear models (105) into a combined linear model (145). Two or more linear models and an observation of interest (107) are selected (210; 220). The linear models are concurrent with respect to the observation of interest. The observation of interest includes a class value and a feature vector (109). A distance is selected (230), and a plurality of feature vectors are selected that are within the distance of the feature vector associated with the observation of interest (240). These feature vectors are input to the selected linear models and a plurality of class values are generated. These class values and the selected feature vectors are used to generate a combined linear model (250). The combined model is either a mean local linear surrogate model or a linearly weighted local surrogate model.
Systems and methods are provided for dynamically adjusting a website of an entity using information that has been received, stored, gathered, and/or otherwise obtained about what people want to find on the entity's website. A website may be dynamically adjusted using trending information. Dynamically adjusting may comprise generating and presenting links on the website to webpages in order of volume over a defined time threshold, or by variance over a standard volume over a longer established time frame. Dynamically adjusting the website may comprise providing an element on a website for what is most urgent to customers. A unit associated with a website may be monitored, and when the unit volume or activity starts to spike beyond normal expectations, then information about the unit is proactively and/or preemptively offered on the website, or a webpage of the website, without ever having a conversation with a user.
Systems (205) and methods (300; 400) are described to determine anomalies and identify segments (231) associated with the anomalies (222). Surveys (136) are collected over a period of time to create historical data (221). The surveys include questions related to customer experience ("CX") and questions that can be used to divide the customers into one or more segments. When a survey is received from a customer, the scores of the survey are compared with scores of the historical data (and other currently received scores) to determine if the scores associated with a survey are associated with an anomaly. Once an anomaly is detected, the segments associated with the surveys corresponding to the anomaly are analyzed to determine which segments are associated with the anomaly. The determined segments can be used to correct, solve, or explain the anomaly.
Systems (135) and methods (300;400) for incorporating intelligent virtual assistants into advertisements on social networking platforms are provided. When a user interacts with a content item (115), an intelligent virtual assistant (211) is selected and put into contact with the user. The intelligent virtual assistant is provided with a context (221) that includes information about the user in the social networking platform (120), information about the user in a customer relationship management platform, and information about the product, service, or entity associated with the content item. The context allows the intelligent virtual assistant to converse with the user in a way that feels natural and relevant to the user and allows the intelligent virtual assistant to answer any questions about the product, service, or entity associated with the content item.
An external content engine (116) automatically monitors content items generated by external data sources such as online merchants, social networking platforms, and discussion forums for an entity (310). The monitored content items may include public messages such as posts, reviews, and comments. When a content item is identified that references or relates to the entity (320), natural language processing is used to determine if the content item has a positive or negative context (330). The external content engine may then determine an action to take based on the context and other factors such as a popularity or influence of the author of the content item (340).
A system and method using blockchain for monitoring and tracking service provider involvement in a transaction on behalf of a customer company. In the system and method, session information related to the transactions are encrypted using an encryption key specific to a company on whose behalf the service provider is acting. The encrypted action is signed the with a private key of a public/private key pair. The signed, encrypted action record is placed on the blockchain, which can later be accessed to review the actions on behalf of the specific company.
Systems and methods are described to automatically generate candidate questions and responses to speed the process of response creation and editing for commercial IVAs and chatbots. Rather than create the questions and responses from scratch for a new IVA, the system uses existing questions and responses from a previous or related IVA to train a model that can generate proposed responses to provided questions. The model, or a different model, can further be trained to generate responses using data taken from company or entity-specific data sources such as websites and knowledge bases. After a set of questions and responses have been generated for an IVA they may be reviewed by one or more human reviewers to ensure they are of a suitable quality. Where no previous or related IVA exists to provide example responses, the model may be trained solely using the company or entity-specific data.
A system and method for updating computerized language models is provided that automatically adds or deletes terms from the language model to capture trending events or products, while maximizing computer efficiencies by deleting terms that are no longer trending and use of knowledge bases, machine learning model training and evaluation corpora, analysis tools and databases.
Attention weights in a hierarchical attention network indicate the relative importance of portions of a conversation between an individual at one terminal and a computer or a human agent at another terminal. Weighting the portions of the conversation after converting the conversation to a standard text format allows for a computer to graphically highlight, by color, font, or other indicator visible on a graphical user interface, which portions of a conversation led to an escalation of the interaction from an intelligent virtual assistant to a human customer service agent.
Systems and methods for analyzing communication sessions are provided. A representative method includes: recording the communication session; identifying those portions of the communication session not containing speech of at least one of the agent and the customer; and performing post-recording processing on the recording of the communication session based, at least in part, on whether the portions contain speech of at least one of the agent and the customer.
Methods and systems are presented for integrating workforce management and quality monitoring. In one embodiment, the method comprises the steps of: receiving information about a skill; capturing a plurality of contacts made by an agent; receiving an evaluation of the contacts; and updating the skill information based on the evaluation. The skill is associated with an agent, and the evaluation measures the agent skill. In another embodiment, the method comprises the steps of: receiving information about a skill; capturing a plurality of contacts made by an agent; receiving an evaluation form for the contacts; and updating the form based on the skill information. The skill is associated with an agent, and the form produces a measurement of the agent skill.
Systems and methods are disclosed for providing secure, captured data in a customer center. In one embodiment, the method comprises: capturing data with a recording system; receiving a request to retrieve electronic keys for encrypting the data; responsive to receiving the request, transmitting the electronic keys to the recording system; encrypting the data using the electronic keys; associating the electronic keys with the encrypted data; and storing the encrypted data in the recording system.
Included are systems and methods for distributive network control. Also embodiment of a method includes receiving an indication related to recording data stored on a local cache and determining whether to remotely store at least a portion of the data. Some embodiments include sending a request for the stored data.
Systems and methods for providing recording as a network service are provided. A representative method incorporates: communicating instructions to a network, the instructions indicating that IP packets associated with a communication that is to be recorded are to be directed to long term storage such that the network: receives the instructions; determines whether Internet Protocol (IP) packets, which are being communicated by the network, are associated with a communication that is to be recorded; and directs information corresponding to the IP packets associated with the communication to a long term storage device.
H04L 12/50 - Circuit switching systems, i.e. systems in which the path is physically permanent during the communication
G06F 3/06 - Digital input from, or digital output to, record carriers
G06F 12/00 - Accessing, addressing or allocating within memory systems or architectures
G11B 11/00 - Recording on, or reproducing from, the same record carrier wherein for these two operations the methods or means are covered by different main groups of groups or by different subgroups of group ; Record carriers therefor
G11B 13/00 - Recording simultaneously or selectively by methods or means covered by different main groups; Record carriers therefor; Reproducing simultaneously or selectively therefrom
Systems and methods for recording communications are provided. In this regard, a representative system incorporates recording resources and a recording controller. The recording resources are operative to record information corresponding to communications, with the communications being provided in multiple communication formats and/or involving devices and paths with varying characteristics and capabilities. The recording controller is communicatively coupled to each of the recording resources. The recording controller is operative to: monitor the communications; determine suitability and availability of the recording resources for recording the communications; analyze a recording hierarchy; and allocate at least an available one of the recording resources for recording a designated one of the communications based on the suitability and availability determined and the recording hierarchy.
H04M 1/64 - Automatic arrangements for answering calls; Automatic arrangements for recording messages for absent subscribers; Arrangements for recording conversations
37.
SYSTEMS AND METHODS FOR SCHEDULING CONTACT CENTER AGENTS
Systems and methods for scheduling contact center agents are provided. In this regard, a representative method includes: receiving information corresponding to work schedules and skills of agents of a remote contact center that shares contacts with a local contact center; correlating the skills with skills that are to be used for scheduling agents of the local contact center; and generating work schedules for the agents of the local contact center based, at least in part, on a correlation between the skills of the agents of the remote contact center and the local contact center, and an evaluation of the work schedules of the agents of the remote contact center.